Research on Active Queue Management of Delay Network Based on Adaptive Control
Sun Yan-fei① Zhang Shun-yi① Wang Pan① Zhou Lei② Shi Jin③ ①(Jiangsu Province Eng. Research Center of Telecomm. & Network Tech., Nanjing Univ. of Posts and Telecomm., Nanjing 210003, China) ②(State Key Lab. of Integrated Service Networks, Xidian University, Xi’an 710071, China ) ③(State Key Lab. of Novel Software Technology, Nanjing University, Nanjing 210093, China)
Enhancing Active Queue Management (AQM) algorithm’s self-adapting and overcoming network delay’s poor effect are research emphases. After analyzing traditional PID control algorithm’s limitation, a novel active queue management algorithm for delay network based on Fuzzy Adaptive PID control and Gray-prediction (FAGPID) is proposed, which can achieve PID parameters’ on-line self-adapting by fuzzy control under the dynamic delay network circumstances. And, a gray-prediction algorithm is successfully introduced into feedback data’s advanced prediction to compensate delay. Contrasted with traditional PID and FIGPID (Fuzzy Immue Gray-prediction PID) by simulations, FAGPID has equivalent performance to FIGPID and has better performance than traditional PID control. Both FAGPID and FIGPID can converge to queue size-setting value rapidly and stably, and get lesser packets loss rate, but FAGPID’s algorithm complexity is lower.